Type ReduceLROnPlateau
Namespace tensorflow.keras.callbacks
Parent Callback
Interfaces IReduceLROnPlateau
Reduce learning rate when a metric has stopped improving. Models often benefit from reducing the learning rate by a factor
of 2-10 once learning stagnates. This callback monitors a
quantity and if no improvement is seen for a 'patience' number
of epochs, the learning rate is reduced. Example:
Show Example
reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.2,
patience=5, min_lr=0.001)
model.fit(X_train, Y_train, callbacks=[reduce_lr])
Methods
Properties
Public instance methods
bool in_cooldown()
object in_cooldown_dyn()
Public static methods
ReduceLROnPlateau NewDyn(ImplicitContainer<T> monitor, ImplicitContainer<T> factor, ImplicitContainer<T> patience, ImplicitContainer<T> verbose, ImplicitContainer<T> mode, ImplicitContainer<T> min_delta, ImplicitContainer<T> cooldown, ImplicitContainer<T> min_lr, IDictionary<string, object> kwargs)
Initialize self. See help(type(self)) for accurate signature.